Medium severity · published Apr 6, 2026
CVE-2026-34753
vLLM affected by Server-Side Request Forgery (SSRF) in `download_bytes_from_url `
5.4
CVSS
0.2%
EPSS
No
On KEV
Description
vLLM is an inference and serving engine for large language models (LLMs). From 0.16.0 to before 0.19.0, a server-side request forgery (SSRF) vulnerability in download_bytes_from_url allows any actor who can control batch input JSON to make the vLLM batch runner issue arbitrary HTTP/HTTPS requests from the server, without any URL validation or domain restrictions.
This can be used to target internal services (e.g. cloud metadata endpoints or internal HTTP APIs) reachable from the vLLM host. This vulnerability is fixed in 0.19.0.
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:L
Attack vector
Network
Complexity
Low
Privileges
Low
User interaction
None
Confidentiality
Low
Integrity
None
Availability
Low
Scope
Unchanged
Exploitation
Is it being used?
Exploit prediction (EPSS)0.2% · higher than 16% of CVEs
Exploited in the wildNo evidence yet
CISA KEVNot listed
Ransomware campaign useNot known
Affected products
Which versions
VL
vllm · vllm-project
>= 0.16.0, < 0.19.0 · source: vendor, NVD
References
NVD
https://nvd.nist.gov/vuln/detail/CVE-2026-34753
CVE.org
https://www.cve.org/CVERecord?id=CVE-2026-34753
Patch
https://github.com/vllm-project/vllm/security/advisories/GHSA-pf3h-qjgv-vcpr
More from vllm
9.8
CVE-2026-115915
vLLM: Untrusted EPS inputs can trigger denial of service or Ghostscript RCE
9.8
CVE-2026-25960
SSRF Protection Bypass in vLLM
9.8
CVE-2026-22778
vLLM leaks a heap address when PIL throws an error
9.8
CVE-2026-22807
vLLM affected by RCE via auto_map dynamic module loading during model initialization
9.8
CVE-2024-9053
vllm-project vllm version 0.6.0 contains a vulnerability in the AsyncEngineRPCServer() RPC server entrypoints